---
title: multilingual-e5-large
canonical_url: "https://www.modelscope.cn/models/Xorbits/multilingual-e5-large"
md_url: "https://www.modelscope.cn/models/Xorbits/multilingual-e5-large.md"
repository: Xorbits/multilingual-e5-large
last_updated: 2023-10-19
license: "Apache License 2.0"
model_type:
  - xlm-roberta
architectures:
  - XLMRobertaModel
parameters: 559.9M
tensor_type:
  - I64
  - F32
library_name:
  - onnx
  - safetensors
  - xinference
frameworks:
  - xinference
inference_backends:
  - "deploy_task emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2344
stars: 3
---

# multilingual-e5-large

> multilingual-e5-large - Xorbits 在 ModelScope 开源的模型。multilingual-e5-large

Xorbits/multilingual-e5-large 是 ModelScope 魔搭社区上的 559.9M 参数机器学习模型，采用 Apache License 2.0 许可，可用 deploy_task emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: Xorbits/multilingual-e5-large
- **License**: Apache License 2.0
- **Parameters**: 559.9M
- **Inference backends**: deploy_task emb, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 2344
- **Stars**: 3
- **Last updated**: 2023-10-19

Source: https://www.modelscope.cn/models/Xorbits/multilingual-e5-large

---

## multilingual-e5-large

This repo contains embedding model files for multilingual-e5-large.

FlagEmbedding can map any text to a low-dimensional dense vector 
which can be used for tasks like retrieval, classification, clustering, or semantic search. 
And it also can be used in vector databases for LLMs.

## Information
- dimensions: 1024
- max_tokens: 514
- language: zh

## Usage

###  Start a local instance of Xinference
```bash
xinference -p 9997
```

### Launch and inference
```python
from xinference.client import Client

client = Client("http://localhost:9997")
model_uid = client.launch_model(model_name="multilingual-e5-large", model_type="embedding")
model = client.get_model(model_uid)

model.create_embedding("write a poem.")
```